|
--- |
|
license: apache-2.0 |
|
base_model: google-bert/bert-base-multilingual-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- precision |
|
- recall |
|
- f1 |
|
model-index: |
|
- name: result-colab |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# result-colab |
|
|
|
This model is a fine-tuned version of [google-bert/bert-base-multilingual-uncased](https://huggingface.co/google-bert/bert-base-multilingual-uncased) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4210 |
|
- Accuracy: 0.9083 |
|
- Precision: 0.9076 |
|
- Recall: 0.9099 |
|
- F1: 0.9085 |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 1e-05 |
|
- train_batch_size: 64 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- num_epochs: 8 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:| |
|
| 0.11 | 1.0 | 24 | 0.4032 | 0.8991 | 0.9040 | 0.8991 | 0.8980 | |
|
| 0.0824 | 2.0 | 48 | 0.4500 | 0.8853 | 0.8806 | 0.8874 | 0.8810 | |
|
| 0.0901 | 3.0 | 72 | 0.4908 | 0.8716 | 0.8809 | 0.8576 | 0.8653 | |
|
| 0.0554 | 4.0 | 96 | 0.4473 | 0.8991 | 0.9059 | 0.8943 | 0.8984 | |
|
| 0.0612 | 5.0 | 120 | 0.4675 | 0.8807 | 0.8867 | 0.8723 | 0.8766 | |
|
| 0.0508 | 6.0 | 144 | 0.4011 | 0.9220 | 0.9228 | 0.9191 | 0.9203 | |
|
| 0.0513 | 7.0 | 168 | 0.4161 | 0.9083 | 0.9049 | 0.9098 | 0.9070 | |
|
| 0.049 | 8.0 | 192 | 0.4210 | 0.9083 | 0.9076 | 0.9099 | 0.9085 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.4 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|